A statistical process employed to find out whether or not there’s a statistically vital distinction between the technique of two impartial populations. This take a look at depends on the idea that the inhabitants normal deviations are recognized or that the pattern sizes are sufficiently giant to approximate them. For instance, it might be used to match the typical take a look at scores of scholars from two completely different colleges, offered that the inhabitants normal deviations of take a look at scores for every faculty are recognized.
This technique is important as a result of it permits researchers and analysts to make knowledgeable choices based mostly on information. It supplies a framework for assessing if noticed variations are probably resulting from an actual impact or just random variation. Traditionally, the event and utility of this method has been instrumental in numerous fields, from medical analysis evaluating therapy efficacy to high quality management in manufacturing assessing manufacturing consistency.
The next sections will delve into the particular assumptions required for legitimate implementation, the steps concerned in performing the calculation, and the interpretation of the ensuing take a look at statistic and p-value, in addition to discover eventualities the place different statistical assessments could be extra acceptable.
1. Unbiased samples
The validity of a process used to match inhabitants means relies upon critically on the independence of the samples being analyzed. Unbiased samples suggest that the observations in a single pattern are unrelated to the observations within the different pattern. This assumption immediately impacts the calculation of the usual error, which is a key element in computing the take a look at statistic. If samples will not be impartial, the usual error will probably be miscalculated, probably resulting in incorrect conclusions concerning the distinction between the inhabitants means. As an example, if analyzing the effectiveness of a coaching program by evaluating pre- and post-training scores of the identical people, the samples are inherently dependent, and an evaluation designed for impartial samples can be inappropriate.
Take into account a sensible utility in advertising and marketing. If an organization needs to evaluate the effectiveness of two completely different promoting campaigns on separate, randomly chosen buyer teams, the responses of consumers uncovered to marketing campaign A needs to be impartial of the responses of these uncovered to marketing campaign B. If these teams have been one way or the other associated (e.g., members of the identical family), the independence assumption can be violated, probably skewing the statistical outcomes. The results of neglecting the independence assumption can vary from inflated Kind I error charges (incorrectly rejecting a real null speculation) to lowered statistical energy (failing to detect a real distinction when one exists). Due to this fact, verifying the independence of samples is a vital step earlier than implementing a statistical take a look at evaluating inhabitants means.
In abstract, the independence of samples will not be merely a technical element however a foundational requirement that underpins the accuracy and reliability of statistical conclusions. Failure to make sure independence can result in deceptive outcomes and flawed decision-making. Recognizing and addressing potential dependencies between samples is essential for making certain the integrity of statistical evaluation.
2. Identified normal deviations
The applicability of a statistical comparability rests on the data of inhabitants normal deviations. This requirement stems from the tactic’s reliance on the conventional distribution as a mannequin for the sampling distribution of the distinction between means. When inhabitants normal deviations are recognized, the take a look at statistic will be calculated immediately, offering a quantifiable measure of the discrepancy between pattern means relative to the anticipated variability. The absence of this information necessitates different procedures that estimate the inhabitants normal deviations from the pattern information, introducing extra uncertainty into the evaluation. In contexts the place historic information or established analysis supplies dependable estimates of inhabitants variability, this statistical technique gives a sturdy method for assessing variations between two impartial teams. For instance, in standardized academic testing, the inhabitants normal deviation of take a look at scores could also be well-established from prior years, permitting researchers to effectively evaluate the efficiency of scholars from completely different colleges or educational applications.
Nonetheless, the idea of recognized inhabitants normal deviations is commonly not met in apply. In lots of analysis settings, the true inhabitants variability is unknown and should be estimated from the pattern information. When pattern sizes are sufficiently giant (usually n > 30), the pattern normal deviations present affordable approximations of the inhabitants normal deviations, and this technique can nonetheless be utilized with warning. In conditions with smaller pattern sizes and unknown inhabitants normal deviations, different strategies, reminiscent of a t-test, are extra acceptable. The t-test accounts for the extra uncertainty launched by estimating the inhabitants normal deviations, leading to a extra conservative evaluation of the statistical significance. Due to this fact, cautious consideration of the underlying assumptions and the supply of details about inhabitants variability is important for choosing the suitable statistical take a look at.
In conclusion, the situation of recognized inhabitants normal deviations is a defining attribute of this statistical comparability, influencing its applicability and interpretation. Whereas it gives a strong device for evaluating means when this assumption is legitimate, researchers should concentrate on its limitations and take into account different approaches when inhabitants normal deviations are unknown or poorly estimated. Understanding the function of this assumption is essential for correct statistical inference and knowledgeable decision-making.
3. Normality assumption
The legitimate utility of a statistical technique that assesses variations between two inhabitants means necessitates adherence to particular assumptions. A main assumption facilities on the distribution of the underlying populations, particularly the idea of normality. This part explores the normality assumption and its implications for the right implementation.
-
Central Restrict Theorem Utility
Even when the populations themselves will not be completely usually distributed, the Central Restrict Theorem (CLT) states that the sampling distribution of the pattern means will method a standard distribution because the pattern measurement will increase. That is significantly related when coping with pattern sizes better than 30. Within the context, the CLT permits for the tactic to be utilized even when the populations will not be strictly regular, offered the pattern sizes are sufficiently giant to make sure that the sampling distribution of the distinction in means is roughly regular. Failure to satisfy this situation could invalidate the outcomes.
-
Impression of Non-Normality on Check Statistic
The calculation of the take a look at statistic assumes that the info follows a standard distribution. If the underlying information deviates considerably from normality, the calculated take a look at statistic could not precisely mirror the true distinction between the inhabitants means. In such circumstances, the p-value, which is derived from the take a look at statistic, could also be unreliable, resulting in incorrect conclusions concerning the statistical significance of the noticed distinction. The presence of outliers or skewness within the information can additional exacerbate these points, probably resulting in inflated Kind I error charges (incorrectly rejecting a real null speculation).
-
Assessing Normality
Previous to making use of the statistical comparability, it’s essential to evaluate the normality of the underlying information or the sampling distribution. This may be achieved by means of numerous graphical and statistical strategies. Histograms and Q-Q plots can visually assess the form of the info distribution and determine deviations from normality. Statistical assessments, such because the Shapiro-Wilk take a look at or the Kolmogorov-Smirnov take a look at, present a extra formal evaluation of normality. If vital deviations from normality are detected, different non-parametric assessments, which don’t depend on the normality assumption, needs to be thought-about.
-
Transformations to Obtain Normality
In some circumstances, information transformations will be utilized to make the info extra intently resemble a standard distribution. Widespread transformations embrace logarithmic transformations, sq. root transformations, and inverse transformations. These transformations might help to cut back skewness and make the info extra appropriate for evaluation utilizing this technique. Nonetheless, you will need to word that transformations can even have an effect on the interpretation of the outcomes, and cautious consideration needs to be given to the implications of any transformations utilized.
In abstract, the normality assumption performs a essential function within the legitimate utility of the “2 pattern z take a look at”. Whereas the Central Restrict Theorem supplies some robustness towards deviations from normality, it’s important to evaluate the normality of the info or the sampling distribution and take into account different assessments or transformations when acceptable. Failure to handle the normality assumption can result in inaccurate outcomes and flawed conclusions. Due to this fact, an intensive understanding of the normality assumption and its implications is essential for accountable statistical evaluation.
4. Speculation formulation
The exact articulation of hypotheses kinds a foundational factor within the utility of a statistical technique designed to judge variations between inhabitants means. Clear hypotheses dictate the route and interpretation of the evaluation, offering a framework for assessing the proof offered by the info.
-
Null Speculation (H0)
The null speculation posits that there isn’t any vital distinction between the technique of the 2 populations. Within the context of evaluating the effectiveness of two educating strategies, the null speculation would state that the typical efficiency of scholars taught by technique A is the same as the typical efficiency of scholars taught by technique B. The analytical process goals to evaluate the proof towards this assertion. Failure to reject the null speculation doesn’t essentially show its fact, however moderately signifies that there’s inadequate proof to conclude a distinction exists.
-
Various Speculation (H1)
The choice speculation contradicts the null speculation, proposing a particular relationship between the inhabitants means. This will take a number of kinds: a two-tailed speculation asserting that the means are merely completely different, or one-tailed hypotheses specifying that one imply is both better than or lower than the opposite. If evaluating a brand new drug in comparison with a placebo, a one-tailed different speculation may state that the typical end result for sufferers receiving the drug is larger than the typical end result for these receiving the placebo. The selection of a one-tailed versus a two-tailed take a look at will depend on the analysis query and the directionality of the anticipated impact.
-
Directionality and Check Choice
The directional nature of the choice speculation immediately impacts the choice and interpretation of the statistical process. A two-tailed take a look at assesses variations in both route, whereas a one-tailed take a look at focuses completely on variations in a pre-specified route. Deciding on an inappropriate take a look at based mostly on the speculation can result in inaccurate conclusions. For instance, if a researcher anticipates {that a} new fertilizer will improve crop yield, a one-tailed take a look at is acceptable. Nonetheless, if the researcher is just fascinated with whether or not the fertilizer has any impact, no matter route, a two-tailed take a look at is warranted.
-
Impression on P-value Interpretation
The formulation of the speculation basically shapes the interpretation of the p-value. The p-value represents the chance of observing a take a look at statistic as excessive as, or extra excessive than, the one calculated from the pattern information, assuming the null speculation is true. In a one-tailed take a look at, the p-value represents the chance of observing a end result within the specified route, whereas in a two-tailed take a look at, the p-value represents the chance of observing a end in both route. Due to this fact, the speculation should be fastidiously thought-about when deciphering the p-value to find out the statistical significance of the findings.
In abstract, the clear and exact formulation of each the null and different hypotheses is essential for the suitable and significant utility of the statistical technique. These hypotheses information the collection of the take a look at, affect the interpretation of the p-value, and finally decide the conclusions drawn from the evaluation. A poorly formulated speculation can result in deceptive outcomes and flawed decision-making.
5. Check statistic calculation
The computation of a take a look at statistic constitutes a pivotal step within the implementation of a statistical technique designed to evaluate variations between inhabitants means. This numerical worth encapsulates the magnitude of the noticed distinction relative to the anticipated variability, serving as the idea for evaluating the proof towards the null speculation.
-
Formulation and Parts
The take a look at statistic is usually calculated utilizing a components that includes the pattern means, inhabitants normal deviations (if recognized), and pattern sizes. The final kind includes subtracting one pattern imply from the opposite, then dividing by the usual error of the distinction between the means. The usual error quantifies the anticipated variability within the pattern imply distinction resulting from random sampling. A bigger take a look at statistic signifies a better discrepancy between the pattern means relative to the anticipated variability, suggesting stronger proof towards the null speculation. For instance, if evaluating the typical gross sales of two completely different advertising and marketing campaigns, a big take a look at statistic means that the noticed distinction in gross sales is unlikely to be resulting from likelihood alone.
-
Affect of Pattern Measurement
Pattern measurement performs an important function within the magnitude and interpretation of the take a look at statistic. Bigger pattern sizes are likely to end in smaller normal errors, thereby inflating the take a look at statistic even when the precise distinction between the pattern means stays fixed. This phenomenon displays the elevated precision afforded by bigger samples in estimating inhabitants parameters. Consequently, when evaluating two populations with comparable pattern imply variations, the statistical technique based mostly on giant samples could yield a extra statistically vital end result than one based mostly on small samples. Take into account a pharmaceutical firm testing the efficacy of a brand new drug; a bigger pattern measurement would supply extra statistical energy to detect a real impact, even when the impact measurement is comparatively small.
-
Impression of Normal Deviation
The inhabitants normal deviations additionally exert a direct affect on the calculation of the take a look at statistic. Bigger normal deviations point out better variability throughout the populations, resulting in bigger normal errors and, consequently, smaller take a look at statistics. This displays the elevated uncertainty in estimating the inhabitants means when the info is extra dispersed. Conversely, smaller normal deviations end in smaller normal errors and bigger take a look at statistics, indicating better confidence within the noticed distinction between the pattern means. As an example, in manufacturing, if the usual deviation of product dimensions is small for 2 completely different manufacturing traces, even a slight distinction within the common dimensions could yield a statistically vital take a look at statistic.
-
Check Statistic and P-value
The take a look at statistic serves because the enter for figuring out the p-value, which represents the chance of observing a take a look at statistic as excessive as, or extra excessive than, the one calculated from the pattern information, assuming the null speculation is true. A smaller p-value signifies stronger proof towards the null speculation. The p-value is obtained by evaluating the take a look at statistic to a recognized chance distribution, reminiscent of the usual regular distribution. The precise distribution used will depend on the assumptions underlying the statistical technique. For instance, a take a look at statistic of two.58 would have a p-value of 0.01 in a two-tailed take a look at. This connection between the take a look at statistic and p-value is essential as a result of it permits researchers to quantify the energy of proof towards the null speculation and make knowledgeable choices about whether or not to reject it.
In abstract, the computation of the take a look at statistic is a essential step in assessing variations between inhabitants means. It encapsulates the noticed distinction relative to the anticipated variability and serves as the idea for figuring out the p-value and making inferences concerning the inhabitants. Understanding the elements of the take a look at statistic, together with the pattern means, normal deviations, and pattern sizes, is important for the right interpretation and utility of the statistical technique.
6. P-value willpower
The willpower of the p-value is a essential step in a statistical technique designed to evaluate the distinction between two inhabitants means. It quantifies the chance of observing a take a look at statistic as excessive as, or extra excessive than, the one calculated from the pattern information, assuming the null speculation is true. Its function is central to creating inferences concerning the inhabitants from the pattern information.
-
Definition and Interpretation
The p-value supplies a measure of the proof towards the null speculation. A smaller p-value signifies stronger proof towards the null speculation, suggesting that the noticed distinction between pattern means is much less prone to have occurred by likelihood. Conversely, a bigger p-value means that the noticed distinction is extra prone to be resulting from random variation. For instance, a p-value of 0.03 signifies that there’s a 3% likelihood of observing a take a look at statistic as excessive as, or extra excessive than, the one calculated, assuming the null speculation is true.
-
Calculation Methodology
The p-value is calculated by evaluating the take a look at statistic to a recognized chance distribution, usually the usual regular distribution, given the assumptions of the statistical technique. The take a look at statistic is transformed right into a chance worth based mostly on the traits of this distribution. In a two-tailed take a look at, the p-value represents the realm beneath the curve in each tails past the noticed take a look at statistic values. In a one-tailed take a look at, the p-value represents the realm beneath the curve within the tail equivalent to the route specified within the different speculation. For instance, if the calculated take a look at statistic is 1.96 and a two-tailed take a look at is used, the p-value is roughly 0.05.
-
Relationship to Significance Degree
The p-value is in comparison with a predetermined significance degree (alpha), usually set at 0.05, to find out whether or not to reject the null speculation. If the p-value is lower than or equal to the importance degree, the null speculation is rejected, and the outcomes are deemed statistically vital. If the p-value is larger than the importance degree, the null speculation will not be rejected, and the outcomes will not be thought-about statistically vital. In sensible phrases, if researchers set alpha at 0.05 and get a p-value of 0.02, the null speculation is rejected. A p-value of 0.1 would fail to reject the null speculation.
-
Limitations and Misinterpretations
The p-value is commonly misinterpreted because the chance that the null speculation is true or the chance that the noticed impact is because of likelihood. Nonetheless, it’s important to acknowledge that the p-value solely displays the chance of observing the info, or extra excessive information, on condition that the null speculation is true. It doesn’t present details about the magnitude or sensible significance of the noticed impact. Moreover, relying solely on p-values can result in inaccurate conclusions, significantly when pattern sizes are small or when a number of comparisons are made. Take into account that a big pattern measurement will have a tendency to provide a small p-value, even when the impact measurement will not be meaningfully vital.
In abstract, the willpower of the p-value supplies an important piece of proof for making statistical inferences when evaluating inhabitants means. Nonetheless, it’s important to know its limitations and interpret it together with different elements, such because the impact measurement, pattern measurement, and the context of the analysis query. A nuanced understanding of the p-value permits for a extra knowledgeable decision-making course of.
7. Significance degree
The importance degree, denoted as alpha (), serves as a essential threshold in speculation testing. Within the context of a statistical comparability of inhabitants means, alpha determines the chance of incorrectly rejecting the null speculation when it’s, in reality, true. Its choice immediately impacts the decision-making course of and influences the probability of Kind I errors.
-
Definition and Interpretation
The importance degree represents the utmost acceptable chance of a Kind I error. A generally used significance degree is 0.05, indicating a 5% danger of rejecting the null speculation when it’s true. In sensible phrases, if the null speculation is true and this statistical technique is utilized 100 occasions, it’s anticipated that the null speculation will probably be incorrectly rejected in roughly 5 of these situations. This threshold is established earlier than conducting the evaluation to offer a predetermined criterion for evaluating the proof.
-
Affect on Resolution Rule
The importance degree dictates the choice rule for speculation testing. The calculated p-value is in contrast on to alpha. If the p-value is lower than or equal to alpha, the null speculation is rejected. Conversely, if the p-value is larger than alpha, the null speculation will not be rejected. The collection of a particular alpha worth thus units the boundary that determines when the proof towards the null speculation is taken into account sturdy sufficient to warrant its rejection. As an example, if alpha is about at 0.01, a decrease threshold for rejecting the null speculation is established, decreasing the danger of a Kind I error however probably growing the danger of a Kind II error (failing to reject a false null speculation).
-
Impression on Statistical Energy
The importance degree has an inverse relationship with statistical energy, which is the chance of appropriately rejecting a false null speculation. Lowering the importance degree (e.g., from 0.05 to 0.01) reduces the chance of a Kind I error but in addition decreases statistical energy. Because of this a smaller alpha worth makes it harder to detect a real distinction between inhabitants means, probably resulting in a failure to determine an actual impact. Due to this fact, the selection of alpha includes a trade-off between the danger of Kind I and Kind II errors. Researchers should fastidiously take into account the results of every sort of error when deciding on an acceptable significance degree for his or her evaluation.
-
Contextual Concerns
The suitable significance degree will not be a hard and fast worth and needs to be decided based mostly on the particular context of the analysis query. In conditions the place the results of a Kind I error are extreme, reminiscent of in medical analysis evaluating the protection of a brand new drug, a extra stringent significance degree (e.g., 0.01 or 0.001) could also be warranted to attenuate the danger of incorrectly concluding that the drug is secure. Conversely, in exploratory analysis the place the first purpose is to determine potential areas for additional investigation, a much less stringent significance degree (e.g., 0.10) could also be acceptable to extend the probability of detecting probably attention-grabbing results.
In abstract, the importance degree is a vital parameter within the context of a statistical comparability of inhabitants means. It defines the brink for statistical significance and immediately impacts the decision-making course of. The selection of alpha needs to be fastidiously thought-about, making an allowance for the trade-off between the danger of Kind I and Kind II errors, in addition to the particular context and penalties of the analysis query. A well-chosen significance degree ensures that the statistical evaluation supplies a sound foundation for drawing legitimate conclusions concerning the populations being in contrast.
8. Resolution making
Resolution making is inextricably linked to a statistical comparability of inhabitants means. The result of such a take a look at, particularly the p-value relative to the importance degree, immediately informs whether or not to reject the null speculation. This rejection, or failure thereof, necessitates a choice concerning the populations beneath scrutiny. For instance, in evaluating the effectiveness of two distinct advertising and marketing campaigns, the take a look at’s end result would dictate whether or not to undertake the marketing campaign demonstrating superior efficiency based mostly on statistically vital proof. Due to this fact, the analytical technique’s execution inherently culminates in a choice level.
The sensible utility of a statistical comparability in choice making spans quite a few domains. In pharmaceutical analysis, the result of the evaluation evaluating a brand new drug to a placebo determines whether or not the drug proceeds to additional growth and scientific trials. In manufacturing, the take a look at could also be used to match the standard of merchandise from two completely different manufacturing traces. The choice to re-engineer one line or the opposite would depend upon the outcomes of the take a look at. Monetary analysts use this technique to match the efficiency of various funding methods, thereby influencing asset allocation choices. In every state of affairs, the statistical outcomes signify a essential enter right into a broader decision-making course of, influencing useful resource allocation and strategic route.
In the end, choice making based mostly on this statistical technique depends on the correct interpretation of outcomes and understanding the inherent limitations. The take a look at is a device to offer data-driven insights. It’s not an alternative choice to cautious consideration of context and potential confounding elements. The right implementation and cautious interpretation allow knowledgeable and efficient choices in a wide range of sensible settings.
Steadily Requested Questions
The next part addresses widespread inquiries concerning a statistical technique employed for evaluating the technique of two impartial populations.
Query 1: Beneath what situations is a take a look at evaluating the technique of two populations acceptable?
This take a look at is acceptable when the inhabitants normal deviations are recognized, or when pattern sizes are sufficiently giant to reliably estimate them. Moreover, the idea of impartial samples should be happy.
Query 2: What distinguishes a one-tailed from a two-tailed method when assessing variations between inhabitants means?
A one-tailed take a look at is employed when the analysis speculation specifies a directional distinction, positing that one imply is particularly better or lower than the opposite. A two-tailed take a look at is used when the speculation solely signifies that the means differ, with out specifying a route.
Query 3: How does pattern measurement impression the result of this statistical technique?
Bigger pattern sizes usually improve the statistical energy of the take a look at, making it extra prone to detect a real distinction between inhabitants means if one exists. Smaller pattern sizes could result in a failure to reject the null speculation, even when a real distinction exists.
Query 4: What are the potential penalties of violating the idea of impartial samples?
Violating the independence assumption can result in inaccurate estimates of the usual error, probably leading to inflated Kind I error charges (incorrectly rejecting a real null speculation) or lowered statistical energy (failing to detect a real distinction when one exists).
Query 5: How is the p-value interpreted throughout the context of a statistical comparability?
The p-value represents the chance of observing a take a look at statistic as excessive as, or extra excessive than, the one calculated from the pattern information, assuming the null speculation is true. A smaller p-value signifies stronger proof towards the null speculation.
Query 6: When ought to different statistical strategies be thought-about as a substitute of this technique?
Various strategies, reminiscent of a t-test, needs to be thought-about when inhabitants normal deviations are unknown and pattern sizes are small. Non-parametric assessments needs to be thought-about when the normality assumption is violated.
Correct interpretation and utility of this method require an intensive understanding of its underlying assumptions and limitations.
The next sections will talk about associated strategies for analyzing information.
Sensible Steering
Efficient utilization requires cautious consideration of a number of key elements. The following tips purpose to reinforce the accuracy and reliability of its utility.
Tip 1: Confirm Independence. Be sure that the 2 samples being in contrast are actually impartial. Dependence between samples violates a core assumption, probably invalidating the outcomes. For instance, when evaluating therapy teams, be certain that individuals are randomly assigned and that their responses don’t affect each other.
Tip 2: Assess Normality. Whereas the Central Restrict Theorem supplies some robustness, assess the normality of the underlying populations, particularly with smaller pattern sizes. Make use of graphical strategies reminiscent of histograms or Q-Q plots, or statistical assessments just like the Shapiro-Wilk take a look at, to judge normality.
Tip 3: Account for Identified Normal Deviations. Confirm that the inhabitants normal deviations are certainly recognized with affordable certainty. If inhabitants normal deviations are unknown, take into account different assessments, reminiscent of a t-test, significantly when pattern sizes are small.
Tip 4: Formulate Hypotheses Exactly. Outline the null and different hypotheses clearly and exactly. Decide whether or not a one-tailed or two-tailed take a look at is acceptable based mostly on the analysis query. An ambiguous speculation can result in misinterpretation of the p-value.
Tip 5: Interpret P-values Cautiously. The p-value represents the chance of observing the info, or extra excessive information, on condition that the null speculation is true. It doesn’t point out the chance that the null speculation is true. Keep away from equating statistical significance with sensible significance.
Tip 6: Take into account Impact Measurement. Whereas statistical significance is essential, additionally assess the impact measurement, which quantifies the magnitude of the noticed distinction. A statistically vital end result with a small impact measurement is probably not virtually significant.
These sensible insights will optimize the applying and interpretation of the tactic, enhancing the validity of inferences drawn from the info.
The following part supplies a concluding abstract of the mentioned ideas.
Conclusion
The previous dialogue has explored the elemental ideas and sensible issues surrounding using “2 pattern z take a look at”. This statistical process, when utilized appropriately, supplies a rigorous framework for evaluating the technique of two impartial populations, assuming recognized inhabitants normal deviations or sufficiently giant pattern sizes. Key components embrace verifying independence, assessing normality, formulating exact hypotheses, and deciphering p-values inside context.
Mastery of this statistical method empowers researchers and analysts to attract legitimate inferences and make knowledgeable choices based mostly on empirical information. Ongoing diligence in understanding and making use of its underlying assumptions stays important for accountable and dependable statistical apply. Additional examine of associated strategies reminiscent of t-tests and non-parametric options will present a extra complete skillset for information evaluation.
