| Summary: | 碩士 === 國立臺北大學 === 國際財務金融碩士在職專班 === 102 === There has been a great deal of anecdotal evidence to imply that weather has significant impact on sales of many products. This paper provides empirical evidence to verify if weather effect can also be applied to an apparel brand in department stores. Specifically, the daily sales of an apparel brand are collected and 6 weather variables including air pressure, temperature, humidity, rainfall, sunlight, and cloudiness are analyzed in three methods.
First, the six weather variables are examined individually by bin test to confirm which variable significantly affects the sales. Second, multiple-regression analysis is adopted to prove if there is weather effect in varied sales periods, such as the sales seasons of spring-summer collections and fall-winter collections, the peak and off-peak seasons, etc, in order to eliminate seasonal impact or price influence. Last, I used logistic regression to measure the extent of the weather effect by analyzing which weather variable has significant impact on the possibility of the day sales over the annual average daily sales.
The results show that temperature significantly affects the fall-winter sales while it does not affect the spring-summer sales. By contrast, the rainfall significantly affects the spring-summer sales but it does not affect the fall-winter sales. Additionally, all of the six weather factors have no impact on sales during department store promotion seasons when consumers are more sensitive to price than to weather conditions. In general, temperature and rainfall are the two most significant factors that affect the sales.
|
|---|
